# ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning

arXiv: https://arxiv.org/abs/2007.07936 · HTML: https://mlsanity.com/paper/2007.07936/

## Key facts

- Cited by 209 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 30 of 209)

- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels](https://mlsanity.com/paper/2203.03884/) (2022)
- [ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.05095/) (2021)
- [Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization](https://mlsanity.com/paper/2104.05833/) (2021)
- [Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank](https://mlsanity.com/paper/2104.13415/) (2021)
- [Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.09025/) (2021)
- [LaserMix for Semi-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2207.00026/) (2022)
- [SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.08808/) (2022)
- [Self-Training: A Survey](https://mlsanity.com/paper/2202.12040/) (2022)
- [Bootstrapping Semantic Segmentation with Regional Contrast](https://mlsanity.com/paper/2104.04465/) (2021)
- [Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2104.13613/) (2021)
- [A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation](https://mlsanity.com/paper/2104.07256/) (2021)
- [Context-Aware Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.03557/) (2021)
- [Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation](https://mlsanity.com/paper/2107.11279/) (2021)
- [Semi-supervised Semantic Segmentation with Error Localization Network](https://mlsanity.com/paper/2204.02078/) (2022)
- [Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/2405.05258/) (2024)
- [Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization](https://mlsanity.com/paper/2210.04388/) (2022)
- [Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image Segmentation](https://mlsanity.com/paper/2211.14805/) (2022)
- [Learning Multiple Dense Prediction Tasks from Partially Annotated Data](https://mlsanity.com/paper/2111.14893/) (2021)
- [ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation](https://mlsanity.com/paper/2111.15242/) (2021)
- [PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation](https://mlsanity.com/paper/2211.07609/) (2022)
- [SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance](https://mlsanity.com/paper/2311.16241/) (2023)
- [All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes](https://mlsanity.com/paper/2312.12176/) (2023)
- [Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation](https://mlsanity.com/paper/2104.13243/) (2021)
- [Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2303.01276/) (2023)
- [One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models](https://mlsanity.com/paper/2303.18080/) (2023)
- [Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant](https://mlsanity.com/paper/2301.07340/) (2023)
- [MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks](https://mlsanity.com/paper/2103.06132/) (2021)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2209.07695/) (2022)

## Abstract (arXiv)

The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications. However, progress is limited by the cost of generating labels for training, which sometimes requires hours of manual labor for a single image. Because of this, semi-supervised methods have been applied to this task, with varying degrees of success. A key challenge is that common augmentations used in semi-supervised classification are less effective for semantic segmentation. We propose a novel data augmentation mechanism called ClassMix, which generates augmentations by mixing unlabelled samples, by leveraging on the network's predictions for respecting object boundaries. We evaluate this augmentation technique on two common semi-supervised semantic segmentation benchmarks, showing that it attains state-of-the-art results. Lastly, we also provide extensive ablation studies comparing different design decisions and training regimes.